INDEX

Explanations

numbers and references to legal actions or considerations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-0.83

MigrationBuilder

-0.79

ьажоргаш

-0.72

 invokingState

-0.72

 protoimpl

-0.71

 otomatig

-0.71

ValueStyle

-0.70

 Administrativna

-0.70

 AssemblyCulture

-0.69

 للمعارف

-0.68

POSITIVE LOGITS

 koncep

0.35

 concept

0.33

TestBase

0.32

 potest

0.30

 Concept

0.28

concept

0.25

 introduction

0.25

 trains

0.25

 Jadi

0.25

 Introduction

0.25

Activations Density 0.311%

numbers and references to legal actions or considerations

No Comments

No Known Activations